Guntur Wibawa's repositories
CustomerSegmentSupermarket
Good Seed were employed Data Science for alcohol law compliance. My role includes using specialized cameras at checkout for alcohol buys, applying advanced computer vision for age verification, and designing a model to confirm age. I built a model with ResNet50 and 'relu', using a single neuron to output.
ZuberDataAnalysis
At Chicago's fresh ride-sharing start-up Zuber, my role as an analyst led me on an exciting journey through data. I dived into passenger preferences and explored how weather shifts painted a unique picture of travel habits.
BetaBankChurnAnalysis
Beta Bank is losing customers monthly. Employees want to focus on client retention. As a Data Scientist, I created a model to predict the chance of a customer leaving, based on past behavior and contract terminations.
CarAdPriceAnalysis
In this project, I analyzed Crankshaft List data to identify factors affecting car prices. Analyzing countless vehicle ads, we aimed to provide valuable insights to users for informed car buying/selling decisions.
CreditRiskAnalysis
This project is an endeavor to analyze the Risk of Default in Loan Repayment, with the prime objective being to provide invaluable insights that could be leveraged by banks for credit assessment of potential borrowers.
CustSegmentInsurance
Sure Tomorrow used machine learning to tackle challenges. I assessed its efforts to identify clients for marketing, forecast the chance of new client claims, and ensure better predictive performance, all while safeguarding client privacy without affecting previous models.
GoldPredictionZyfra
As a Data Scientist at Zyfra Company, I developed a predictive model to estimate gold extractable from ore. Using data on extraction and purification, I trained the model to enhance the efficiency of the production process.
IceGameStoreSalesAnalysis
In this project, I have to identify patterns for game success predictions. The project aims to create a potential target hit games for optimal ad campaigns.
MarketOpsVehicleCommerce
Rusty Bargain, a used cars commerce company, is creating an app to attract buyers, let users check vehicle market prices. I'm using historical data on specifications, versions, and pricing to design a model that assesses car values accurately. Focus areas include prediction precision, model efficiency, and training time.
MegalineCBA
As a Data Scientist at Megaline, a leading mobile operator, I developed a model to analyze consumer behavior. I aimed to recommend either the Smart or Ultra package from Megaline's latest offerings, with a minimum accuracy of 0.75.
MusicRecommendationYMusic
As an Analyst in the Y.Music Company, the principal aim for this project is to scrutinize various hypotheses and match user preferences.
OilwellPlacementOilyGiant
I worked with OilyGiant, a petroleum mining firm, to find new oil well locations. I created a model to identify high-profit zones and assessed potential earnings and risks using bootstrapping techniques.
SentimentAnalysisJU
Junky Union is creating a system to sort movie reviews. They aim to train a model to detect negative reviews using the IMBD dataset with polarity labeling. The model must classify reviews as positive or negative with an F1 score of at least 0.85.
SpotifyPopularityProbe
In the digital music era, understanding artist popularity on Spotify is vital. This project taps into Spotify's data, analyzing key factors driving artist prominence. Through our insights, we illuminate what sets successful artists apart in this dynamic platform.
SweetLiftSalesAnalysis
Sweet Lift Taxi collected airport order data. As a Data Scientist, I developed a model to predict taxi orders for the next hour. The goal is to draw more drivers at peak times, targeting an RMSE under 48 on the test set.
TelcoKYCAnalysis
In this project, I examined prepaid packages to analyze customer behavior. The goal was to identify the most profitable package, provide a basis for company marketing budget allocation.
TelecomChurnPrediction
Interconnect seeks to forecast customer churn by analyzing package choices and contracts. If a customer plans to leave, they're offered unique codes and special packages to foster loyalty.